Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Blender Open MCP alvarez868/blender-open-mcp Enables AI agents to control a live Blender session through MCP tools for scene and object manipulation, rendering, PolyHaven asset search/download/texturing, and guided scene workflows, while allowing runtime switching between local or Ope | |
| MCP Personal Server alvarixu/mcp_personal Enables AI models to securely read, write, and query metadata of local files through a controlled file system interface, with support for local and Azure deployment. | |
| Moleculer MCP Bridge alvaroinckot/moleculer-mcp MCP server that exposes Moleculer.js microservice actions as AI tools, enabling AI agents to interact with Moleculer services. | |
| Miinta Pipedrive MCP alvarolloret/pipedrive-mcp Read-only MCP server for Pipedrive that provides a digest-ready sales queue with overdue follow-ups, due today activities, and deals missing next action. | |
| blackout-mcp alvaroluken/blackout Gives any MCP agent exactly-once side effects: each action is recorded with a stable operation ID before it runs, so a crashed or restarted agent reconciles against the target's receipts instead of repeating work, and unknown outcomes escal | |
| mcp-hevo-service alvaromunoz-gk/mcp-hevo-service Read-only MCP server for Hevo Data API, enabling monitoring of pipelines, objects, destinations, models, and workflows with secure self-hosted credentials. | |
| Neo4j MCP Server alvaropaco/neo4j-mcp MCP server for Neo4j that provides abstract graph operations for LLMs, enabling safe and consistent interaction with Neo4j databases through tools like search, insert, update, delete, and schema introspection. | |
| Chisel Planner alvarordev/chisel Enables authenticated MCP clients to manage projects, tasks, habits, and daily capacity through tool calls. | |
| antigravity-mcp alvarosw/antigravity-mcp Enables MCP-compatible coding agents to run the local Antigravity CLI as a coding agent, manage conversation context and common options, and inspect usage, quota, models, version, help, and read-only slash commands. | |
| codex-mcp alvarosw/codex-mcp Enables MCP-compatible coding agents to execute the local Codex CLI as a coding agent, including code reviews, session resume/fork, and CLI diagnostics. | |
| Gemini CLI MCP alvarosw/gemini-cli-mcp Provides MCP clients with a local gateway to the official command-line tool, enabling headless prompts and structured output while automatically rotating API keys on rate-limit responses so long-running sessions are not interrupted. | |
| agent-platform alvaroverona/agent-platform Enables running a local multi-agent pipeline that turns a product idea into a validated technical spec, with tools to generate, deterministically check, LLM-review, and retrieve stored runs. | |
| KPA alvelda/kpa Provides an MCP server for programmatic reading, authoring, editing, designing, and optimization of Apple Keynote presentations. | |
| etsy-mcp alveyautomation/etsy-mcp A production-grade MCP server that enables AI assistants like Claude to read Etsy shop data—listings, orders, inventory, and stats—through eight read-only tools, using OAuth and automatic pagination. | |
| qbo-mcp alveyautomation/qbo-mcp MCP server for QuickBooks Online providing read-only access to customers, vendors, invoices, bills, and chart of accounts. Enables natural language queries to your financial data through Claude or any MCP client. | |
| sellercloud-mcp alveyautomation/sellercloud-mcp The first Model Context Protocol server for SellerCloud. Plug Claude into your catalog, inventory, orders, and channel listings — read-only, in five minutes. | |
| content-qa-mcp alvi-808/content-qa-mcp Enables editorial content QA over the Model Context Protocol with four local tools that analyze readability, AI-sounding language, SEO on-page factors, and produce full reports where every finding includes an actionable fix. | |
| localhostmcp alvii147/localhostmcp Enables LLMs to send HTTP requests to a local development server, allowing interaction with APIs running on localhost. | |
| Google Calendar MCP alvin0727/google-calendar-mcp Enables AI assistants to read, create, update, move, and delete calendar events, list calendars, and query free/busy across multiple independent Google accounts through a single interface, with each account routed explicitly and gated by ro | |
| TimeTree-MCP alvin0919/timetree-mcp Unofficial MCP server for accessing and managing TimeTree calendar data, supporting events, memos, and comments via email/password authentication. | |
| Kimi DeepSeek Subagent alvin20350/dsh_mcp_for_kimiwork Enables Kimi Work and Kimi Code to delegate tasks to existing DeepSeek Harness Desktop workspaces and persistent sessions, including progress checks, steering, cancellation, and recovery. | |
| TinyPNG MCP Server alvinnn1/tinify-mcp Enables batch image compression and resizing using the TinyPNG API. Supports PNG, JPEG, WebP, and AVIF formats with detailed compression reports and multiple resize modes. | |
| Google MCP Server alvinqle/mcp-playground A locally-hosted MCP server that integrates Gmail, Google Calendar, and Google Drive to provide AI-powered management of emails, events, and files. It enables tool-based interactions like sending emails, creating calendar events, and search | |
| a2a-mcp-connector alvintayzhenwei/a2a-mcp-connector Connects AI agents to any standard A2A endpoint, with built-in Agent Card validation. | |
| a2a-raid-mcp alvintayzhenwei/a2a-raid-mcp Enables AI agents to connect to and play a seat in the Agent Raid co-op boss-raid A2A game, using MCP tools to wait for turns, submit moves, and exchange party chat. | |
| logseq-mcp alvinteh-git/logseq-mcp An MCP server for interacting with Logseq graphs, enabling AI assistants to read, create, and manipulate Logseq content. | |
| CodeCompass alvinveroy/codecompass Helps developers tackle legacy codebases by giving AI coding assistants context through Qdrant vector store and Agentic RAG with Ollama or DeepSeek. | |
| Elitepvpers SRO PServer MCP alvis1337/elitepvpers-mcp An MCP server that scrapes elitepvpers.com to provide resources, setup guides, and troubleshooting tools for hosting Silkroad Online private servers. It allows users to search for opcodes, server files, and community releases through natura | |
| precheck alviso/jev-precheck Enables AI agents to get a second signature on writes to systems of record by proxying MCP servers, fetching affected records, deriving comparisons in code, and using Jev to warn or hold doubtful calls before they land. | |
| Hermes Link alvnukov/hermes-link Enables ChatGPT and other MCP clients to operate a local Hermes instance through compact tools for agents, tasks, Kanban boards, schedules, profiles, workers, sessions, workspaces, versioned settings, and events. It supports read/write or r | |
| Attic alvnvnc/attic Enables Alexa+ to maintain and query a long-term household memory over MCP, covering repairs, vendors, prices, warranties, item locations, and unresolved problems. It provides voice-first recall, logging, reminders, and proactive home brief | |
| VisualDoc alvnvnc/visualdoc-mcp MCP server for automated visual-layout QA of DOCX documents, enabling rendering, measurement, rule checking, patching, and diffing in a closed loop. | |
| Chhart-MCP alwank/chhart_mcp MCP for https://chhart.app to easily create flowcharts or sankey diagram | |
| dsh-vision-mcp alwaysalone1/dsh-vision-mcp Enables MCP clients to gain vision capabilities by analyzing images, extracting text, and comparing images through any OpenAI-compatible vision endpoint. | |
| YAPI MCP Server alwaysloveme/yapi-mcp-server Enables LLM clients to browse and inspect YAPI API documentation, including project info, categories, interfaces, and full API details with request/response schemas. | |
| instrumentControl alwaysmy/instrumentcontrol Enables unified discovery, query, and control of laboratory instruments (power supplies, oscilloscopes, signal generators, multimeters) via VISA/SCPI, with device-specific libraries and an MCP server exposing 19 tools for natural language i | |
| DeepL MCP Server alwayssany/deepl-fastmcp-python-server Provides translation capabilities using the DeepL API, supporting text translation between numerous languages, rephrasing, batch translation, document translation, and language detection with formality control. | |
| Multi-Server MCP FastAPI Project alwayssany/fastapi-multi-server-mcp A FastAPI application that hosts multiple MCP servers for weather, news, currency, and quotes APIs. | |
| Food & Nutrition Intelligence MCP Server alwayssany/food-nutrition Provides tools for nutrition data retrieval, meal planning, and dietary analysis using USDA and Edamam APIs, enabling AI-driven dietary insights. | |
| Health API MCP Server alwayssany/health-api Enables interaction with a comprehensive healthcare management system through FastAPI, supporting operations for patients, doctors, appointments, medical records, telemedicine, lab orders, prescriptions, insurance claims, and more with JWT | |
| agent-semaphore alwh1te/agent-semaphore A coordination layer for parallel coding agents that provides intent-carrying claims, conflict prediction, and a serialized landing queue to prevent merge conflicts. | |
| Agent Skills MCP alwicz/agent-skills-mcp Enables Claude to request and receive skills from a database on demand, allowing agents to fetch step-by-step instructions for tasks like lead research while keeping user credentials and execution on the user's own machine. | |
| Website Reader MCP alwikigai/website-reader-mcp Enables AI chat backends to fetch public webpages and obtain cleaned readable text, Markdown, article content, metadata, and summary-ready prompts through MCP tools. | |
| memhub alx-kap/memhub Enables Claude, ChatGPT, and local agents to share one hosted memory layer over the Model Context Protocol, storing per-project state cards and append-only logs as git-versioned markdown with keyword search. Supports conflict-safe state rew | |
| data-filter-mcp alxark/data-filter-mcp Local MCP server that registers restricted Python filters and runs them against local JSON, YAML, and TXT files, enabling safe data filtering and file conversion. | |
| serial-mcp alxgmpr/serial-mcp MCP server that lets LLMs talk to serial devices: microcontrollers, routers, modems, embedded Linux, anything with a UART. | |
| Substack API MCP alxgntv/substack-api-mcp Enables AI agents to draft, publish, and schedule posts on Substack, bypassing the lack of an official publishing API. | |
| upvote-club-apps alxgntv/upvote-club-mcp-apps Interactive MCP server for Upvote.club's public API, featuring a task progress card for get_task_status. | |
| Upvote Club Local MCP alxgntv/upvote-club-mcp-local Enables interaction with the Upvote.club Public API for task management, including creating, deleting, and checking task status, as well as listing platforms and API reference. | |
| Upvote Club Remote MCP alxgntv/upvote-club-mcp-remote Remote MCP server allowing Claude to interact with the Upvote.club API through 7 tools, supporting per-user authentication via X-API-Key header. |
27,801–27,850 of 115,409
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.